GPT-5
GPT-5 is an API-only (closed weights) language model from OpenAI, released August 7, 2025. The context window is 391K tokens. On the Epoch Capabilities Index it scores 150.0, rank 70 of 256 rated models. API price: $1.25 input / $10 output per million tokens.
"We are introducing GPT‑5, our best AI system yet. GPT‑5 is a significant leap in intelligence over all our previous models, featuring state-of-the-art performance across coding, math, writing, health, visual perception, and more.
Check it against your own PC →
Strengths by category
ModelTape's 0–100 fit on Epoch AI benchmark results.
| Category | Score | Based on |
|---|---|---|
| Reasoning | 17.9 | Chess Puzzles, SimpleBench, Mystery Game Puzzles, Humanity's Last Exam |
| Math | 43.0 | ProofBench, MATH level 5, OTIS Mock AIME 2024-2025, FrontierMath-Tiers-1-3-v2-Private, FrontierMath-Tier-4-v2-Private |
| Coding | 43.4 | Aider polyglot, GSO-Bench, MirrorCode, Terminal Bench, SWE-bench Verified |
| Agent | 21.1 | Balrog, Remote Labor Index |
| Knowledge | 73.9 | GPQA diamond, SimpleQA Verified |
Benchmark results
| Benchmark (Epoch AI) | Score |
|---|---|
| MATH level 5 | 98.1% |
| OTIS Mock AIME | 91.4% |
| Aider Polyglot | 88.0% |
| GPQA Diamond | 85.0% |
| SWE-bench Verified | 73.6% |
| FrontierMath (Tiers 1–3) | 58.4% |
| SimpleQA Verified | 50.1% |
| Terminal-Bench | 49.6% |
| SimpleBench | 48.0% |
| Balrog | 32.8% |
| Chess Puzzles | 32.7% |
| Humanity's Last Exam | 25.3% |
| FrontierMath-Tier-4-v2-Private | 22.0% |
| ProofBench | 18.0% |
| Mystery Game Puzzles | 15.2% |
| EBR-bench | 12.7% |
| GSO-Bench | 6.9% |
| MirrorCode | 4.4% |
| Remote Labor Index | 1.7% |
Links
Announcement · Epoch AI benchmarks
Models with a similar score
GLM-5.3-Flash · Muse Spark · GLM-5.2 · Gemini 3 Pro · Claude Sonnet 4.6 · Mistral Large 4 Preview · Qwen 3.8 27B · Gemini 3 Flash
More from OpenAI
GPT-6.1 Terra · GPT-6.1 Sol · GPT-6 Sol · GPT-6 Luna · GPT-6 Astra · GPT-5.6 Cyber · Daybreak Red · Daybreak Blue